A Comparative Study of Detection of Tuberculosis using Machine Learning & Deep Learning

This review paper provides an overview of the comparative studies conducted on the use of machine learning(ML) and deep learning(DL) in the diagnosis of tuberculosis (TB). Deep learning has shown promise as a tool for TB diagnosis, with several studies exploring its use for detection, classification, and prediction. The paper covers the various deep learning models, including convolutional neural networks, recurrent neural networks, and hybrid models, that have been used for TB diagnosis. It also examines the different types of TB data utilized, such as chest X-ray images, sputum smear microscopy, and genomics data. The comparative analysis presented in this review highlights the relative strengths and limitations of each deep learning approach and provides insights into their performance on different TB datasets. Finally, the review discusses the current challenges and future directions for the use of deep learning in TB diagnosis. It is hoped that this review will serve as a useful resource for researchers and clinicians working in this area.